Paper Info
Title
CycleGAN-based Non-parallel Speech Enhancement with an Adaptive Attention-in-attention Mechanism
Abstract
Non-parallel training is a difficult but essential task for DNN-based speech enhancement methods, for the lack of adequate noisy and paired clean speech corpus in many real scenarios. In this paper, we propose a novel adaptive attention-in-attention CycleGAN (AIA-CycleGAN) for non-parallel speech enhancement. In previous CycleGAN-based non-parallel speech enhancement methods, the limited mapping ability of the gen-erator may cause performance degradation and insufficient feature learning. To alleviate this degradation, we propose an integration of adaptive time-frequency attention (ATFA) and adaptive hierarchical attention (AHA) to form an attention-in-attention (AIA) module for more flexible feature learning during the mapping procedure. More specifically, ATFA can capture the long-range temporal-spectral contextual information for more effective feature representations, while AHA can flexibly aggregate different AFTA's intermediate output feature maps by adaptive attention weights depending on the global context. Numerous experimental results demonstrate that the proposed approach achieves consistently more superior performance over previous GAN-based and CycleGAN-based methods in non-parallel training. Moreover, experiments in parallel training verify that the proposed AIA-CycleGAN also outperforms most advanced GAN-based and Non-GAN based speech enhancement approaches, especially in maintaining speech integrity and re-ducing speech distortion.
Year
Venue
DocType
2021
2021 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)
Conference
ISSN
ISBN
Citations 
2640-009X
978-1-6654-4162-9
0
PageRank 
References 
Authors
0.34
0
5
Name
Order
Citations
PageRank
Guochen Yu123.09
Yutian Wang200.34
Chengshi Zheng33211.66
Hui Wang442.86
Qin Zhang5113.75